{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/self-explore-to-avoid-the-pit-improving-the","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","arxiv_id":"2404.10346","date":"2024-04-16","proceeding":null,"authors":["Hyeonbin Hwang","Doyoung Kim","Seungone Kim","Seonghyeon Ye","Minjoon Seo"],"abstract":"Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary models is costly and not scalable. In this paper, we study the problem of whether LLMs could self-improve their reasoning capabilities. To this end, we propose Self-Explore, where the LLM is tasked to explore the first wrong step (i.e., the first pit) within the rationale and use such signals as fine-grained rewards for further improvement. On the GSM8K and MATH test set, Self-Explore achieves 11.57% and 2.89% improvement on average across three LLMs compared to supervised fine-tuning (SFT). Our code is available at https://github.com/hbin0701/Self-Explore.","url_abs":"https://arxiv.org/abs/2404.10346v4","url_pdf":"https://arxiv.org/pdf/2404.10346v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"self-explore-to-avoid-the-pit-improving-the","repo_url":"https://github.com/hbin0701/Self-Explore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.10346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10346"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hbin0701/Self-Explore","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"66b3b5450182da3a","entry":"batch_data","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"code_sha256_prefix":"771d0d0c6a85a612","entry":"check_equation","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/get_rft_data.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/get_rft_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"771d0d0c6a85a612"}},{"code_sha256_prefix":"50408bcb3e87455b","entry":"extract_answer","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/utils_others.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/utils_others.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50408bcb3e87455b"}},{"code_sha256_prefix":"fc107f0a7cb2bb77","entry":"extract_answers","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/utils_others.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/utils_others.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc107f0a7cb2bb77"}},{"code_sha256_prefix":"48f4dfa28740b7de","entry":"get_dataset","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"dpo/prepare_dataset.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/dpo/prepare_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48f4dfa28740b7de"}},{"code_sha256_prefix":"f3a68206b24244ce","entry":"is_eq_correct","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/get_rft_data.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/get_rft_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3a68206b24244ce"}},{"code_sha256_prefix":"c4783f2528e590ab","entry":"read_jsonl","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/get_rft_data.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/get_rft_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c4783f2528e590ab"}},{"code_sha256_prefix":"f5c2fbf1177f0d1f","entry":"standardize_value_str","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/utils_others.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/utils_others.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f5c2fbf1177f0d1f"}},{"code_sha256_prefix":"0ad5c5d201bc2f1e","entry":"get_quantization_config","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"dpo/alignment/model_utils.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/dpo/alignment/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ad5c5d201bc2f1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}